Browse Prior Art Database

Storage Byte Mark Decode With Boundary Recognition

IP.com Disclosure Number: IPCOM000039235D
Original Publication Date: 1987-May-01
Included in the Prior Art Database: 2005-Feb-01
Document File: 2 page(s) / 67K

Publishing Venue

IBM

Related People

LaBalbo, LJ: AUTHOR [+3]

Abstract

Byte marks for data storage are typically generated using the starting address and length, then decoding the appropriate byte marks for each operation. A method that uses the same starting address and length but adds them together eliminates decoding all operations and provides an automatic one-line boundary crossing indication. As seen in an example in Fig. 1, the start address, or pointer, begins the sequence while the sum of the start and length allows the sequence to stop at the appropriate byte mark. (Image Omitted) In the example of an eight-byte store to a four-byte storage bus (Fig. 2), the pointer only uses two of three bits in order to provide a boundary-crossing indicator. The pointer goes only to the first four bytes.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 92% of the total text.

Page 1 of 2

Storage Byte Mark Decode With Boundary Recognition

Byte marks for data storage are typically generated using the starting address and length, then decoding the appropriate byte marks for each operation. A method that uses the same starting address and length but adds them together eliminates decoding all operations and provides an automatic one-line boundary crossing indication. As seen in an example in Fig. 1, the start address, or pointer, begins the sequence while the sum of the start and length allows the sequence to stop at the appropriate byte mark.

(Image Omitted)

In the example of an eight-byte store to a four-byte storage bus (Fig. 2), the pointer only uses two of three bits in order to provide a boundary-crossing indicator. The pointer goes only to the first four bytes. This allows mark generation for a READ/MODIFY/WRITE (RMW) in either word of the eight bytes that does not cross the boundary. On a boundary crossing, byte marks are generated for both words. The first RMW word is stored as its byte marks indicate. The boundary indicator will signal the controls that another RMW is required. The marks for the second word are gated through the AND/OR to storage. This method applies to any configuration where an RMW is required. It requires half the circuitry to implement, as the decoding for the various operations is accomplished automatically. The one-line boundary-crossing indicator can have various uses such as preparing for the next cycle, without the ...